CivArchive
    Fn-Mix Anima-Turbo - v1.0
    NSFW
    Preview 134436819
    Preview 134438738
    Preview 134438739
    Preview 134439028
    Preview 134438956
    Preview 134438962
    Preview 134438969
    Preview 134438980

    模型更新内容 | Update notes:

    • 新版本模型 Fn‑Base‑Anima‑V1.0,针对大量用户想要非 turbo 版本的需求开发。样图虽用了 turbo LoRA 生成,但实测该模型脱离 turbo LoRA 依旧可以产出高质量图像.

    • 新版本模型 Fn‑Base‑Anima‑V1.0 侧重多画师画风还原。样例图单独使用 @deluxe<<<, @imamura ryou, @ogre \(illustogre\) 等画师标签。原生 Anima 对多画师标签适配不佳,本模型着重提取固化画师画风特征。个人实测整体表现优秀;部分画师画风输出偏弱时,可上调标签权重。

    • 推荐使用turbo LoRA获得与例图相同的效果.

    • 如果你喜欢我的模型,不妨点个赞支持一下;如果愿意分享你创作的作品,或是提出对模型的建议,那就再好不过了。感谢大家!

    • The new model, Fn‑Base‑Anima‑V1.0, is developed in response to numerous user requests for a non‑turbo version. Although the sample images were generated using the turbo LoRA, practical tests show this model can still produce high‑quality images without the turbo LoRA.

    • The new Fn‑Base‑Anima‑V1.0 focuses on replicating the art styles of multiple illustrators. Sample images use standalone artist tags such as @deluxe<<<, @imamura ryou, and @ogre (illustogre). The original Anima model has poor compatibility with multi‑illustrator tags; this model prioritizes extracting and embedding stylistic features of various artists. Personal testing demonstrates strong overall performance. If certain illustrator styles render weakly, you may increase the weight of the corresponding tags.

    • It is recommended to use turbo lora to achieve the same effect as the example image.

    • If you like my model, please consider leaving a like to support me. It would be even better if you’re willing to share the images you create or offer suggestions for the model. Thank you all!

    模型介绍 | Introduction:

    • 本模型基于 Anima BASE1.0 模型, 融合多个个人训练LoRa以及Tubro LoRa调整生成.

    • 本模型不需要负面提示词.

    • 当前所有测试皆基于Comfyui, 未在Webui中测试.

    • 受训练素材影响, 模型生成角色可能在无 'halo' 提示词情况下出现光环, 可在提示词中添加 'no halo, no hat' 以解决.

    • This model is based on the Anima BASE1.0 model, generated by integrating multiple personally trained LoRAs for adjustment.

    • This model does not require negative prompts.

    • All current tests are conducted based on Comfyui and have not been tested in Webui.

    • Affected by training materials, the model may generate characters with halos even without the 'halo' prompt, which can be resolved by adding 'no halo, no hat' to the prompt.

    参数推荐 | Recommend:

    • Resolution: 832*1216/1024*1536

    • Steps: 12-16

    • CFG: 1/1.2-1.4 (Adjust the CFG to 1.2–1.4 to enable negative prompts.)

    • Sampler: er_sde/euler/euler_ancestral

    • Scheduler: beta/simple

    • Hires Fix Step: 5

    • Hires Fix CFG: 1

    • Hires Fix Sample: er_sde/euler/euler_ancestral

    • Hires Fix Scheduler: beta/simple

    • Hires Fix Denoise: 0.5

    Description

    FAQ

    Comments (13)

    dan1982kieenJun 21, 2026· 3 reactions
    CivitAI

    Great style!

    fannon
    Author
    Jun 22, 2026

    thank you!

    CECIL2000Jun 22, 2026· 3 reactions
    CivitAI

    超愛大老的模型從NAI就開始用了!
    而且這個還是TURBO的 超讚的

    fannon
    Author
    Jun 22, 2026· 1 reaction

    感谢你的喜欢!

    johnsmith2008Jun 22, 2026· 3 reactions
    CivitAI

    我喜欢你

    fannon
    Author
    Jun 22, 2026· 1 reaction

    我喜欢你, 你喜欢我

    DarkDungeonMasterJun 22, 2026· 2 reactions
    CivitAI

    大佬终于更新anima了好耶,个人非常喜欢这种独特的cute风格。顺便想请教下人物shy, worried, tsundere这类表情下,嘴有点歪歪的这个特征,比如https://civitai.red/images/134438737,用过你以前的模型,都有这个特点,有什么触发条件吗,比如某个特定画师串或提示词,目前靠表情提示词可以触发但是不稳定。也反馈些小问题,比如经常会生成多余的符号,像✨💕❓;提示词如果有black hair几乎总是生成光环,就算加了no halo和负向词加halo仍无法避免,我用的是webui-forge-neo

    fannon
    Author
    Jun 22, 2026· 2 reactions

    谢谢你的喜欢!

    你说的歪嘴应该这个是靠 ':/' 这个tag实现的;

    生成多余的符号这个确实是我数据集准备时的一些失误, 打标和图片处理没做好, 下次应该会改进;

    最后这个black hair这个我测试了一下确实是这样的, 不知为何总是会偏向blue archive中的rio这个角色, 即使我的训练数据集中并没有这个角色的图片, 也可能在我没测试的训练结果下出现了过拟合的问题.

    我认为应该是在生成开始降噪时头顶部位色块会容易在后续降噪时更容易变为光环, 测试了一下使用相近的 'no hat' 可以在大部分情况下避免生成光环, 但也可能会导致角色的头变大, 后续应该也会找办法优化的, 暂时就先使用 'no halo, no hat' 这两个tag改善一下吧.

    感谢反馈!

    DarkDungeonMasterJun 22, 2026

    @fannon 谢谢!

    SEX_TOTOJun 23, 2026
    CivitAI

    有沒有像之前提供工作流參考,這個不是很會使用QAQ

    fannon
    Author
    Jun 24, 2026

    我发布了一个基础的工作流Fn-Mix Anima-Tubro-Workflow, 同时你可以参考Anima模型官方的说明, 下载模型, Text Encoder和VAE并放置于Comfyui的对应位置以使用Anima模型.

    模型位置: .\ComfyUI\models\diffusion_models
    Text Encoder位置: .\ComfyUI\models\text_encoders
    VAE位置: .\ComfyUI\models\vae

    tinklesurge888Jun 26, 2026
    CivitAI

    I have been a big fan of your Fn-EVO Noob XL and always enjoy using it by mixing it with my own LoRAs. What I love most about its default style is that the faces look completely different from the typical AI-generated style!

    I can feel a similar vibe in the facial style of this new model as well, but the overall style feels a lot more like a flat anime art style compared to Fn-EVO NAI.

    Do you have any plans to create a semi-realistic anime style model like Fn-EVO using Anima Turbo in the future?

    Also, do you have a developer community or group on Discord, Telegram, or any other platform?

    fannon
    Author
    Jun 26, 2026· 2 reactions

    Thank you for your appreciation!

    I have indeed been working on a semi-realistic anime-style model. However, unlike NAI or Pony models, I don’t think Anima-based models perform very well with multiple artist tags, but the results from LoRA training are excellent. So I’ve adjusted my approach and now aim more to create a model with an excellent default style. Unfortunately, the current version still doesn’t meet my expectations.

    Also, I don’t have much time and energy, so I haven’t created or joined any communities or groups. AI is just a hobby for me.

    Checkpoint
    Anima

    Details

    Downloads
    876
    Platform
    CivitAI
    Platform Status
    Available
    Created
    6/23/2026
    Updated
    8/16/2026
    Deleted
    -

    Files

    fnMixAnimaTurbo_v10.safetensors

    Mirrors